Arcee AI: Trinity Mini

Arcee AIID: arcee-ai/trinity-mini

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.

Pricing per 1M Tokens

Input (Prompt)$0.04
Output (Completion)$0.15
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length131K
Max Output Tokens131K
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context131K
Top Provider Max Output131K
ModeratedNo

Compare this model

See how Arcee AI: Trinity Mini stacks up against other models.

vs Arcee AI: Trinity Large Preview (free)vs Arcee AI: Trinity Mini (free)vs Arcee AI: Spotlightvs Arcee AI: Maestro Reasoningvs Arcee AI: Virtuoso Large

More from Arcee AI

Arcee AI: Trinity Large Preview (free)
InputFree
Context131K
Arcee AI: Trinity Mini (free)
InputFree
Context131K
Arcee AI: Spotlight
Input$0.18
Context131K
Arcee AI: Maestro Reasoning
Input$0.90
Context131K
Arcee AI: Virtuoso Large
Input$0.75
Context131K

Last updated: March 23, 2026

First tracked: March 23, 2026